Intel Arc B570 vs NVIDIA GeForce RTX 3080 Mobile Comparison

Head-to-Head Benchmarks

The recorded data shows a clear split between these two GPUs, with the NVIDIA GeForce RTX 3080 Mobile taking 7 of the 10 head-to-head benchmark wins, while the Intel Arc B570 manages 3 wins. The most decisive NVIDIA victory comes in the PassMark DirectX 10 test, where the RTX 3080 Mobile scores 120 against the Arc B570's 65, a 84.6% advantage. That is the largest margin in the entire comparison and indicates a substantial lead in legacy DirectX 10 workloads.

The GeForce OpenCL result is nearly as dominant. The RTX 3080 Mobile posts 104831 in Geekbench OpenCL, while the Arc B570 scores 83514, giving the NVIDIA part a 25.5% edge. This is a meaningful gap for compute-oriented tasks that rely on OpenCL acceleration. In the PassMark DirectX 11 test, the RTX 3080 Mobile again leads, scoring 146 versus 118, a 23.7% improvement. The 3DMark Steel Nomad DX12 test, however, tells a different story: the Arc B570 edges out the RTX 3080 Mobile by a razor-thin margin, 2649 to 2644, a delta of only -0.2%. That is within run-to-run variance, but the database records it as a win for Intel.

The Geekbench Vulkan result shows the RTX 3080 Mobile ahead by a moderate 7.5%, with scores of 104066 and 96844 respectively. In PassMark DirectX 9, the NVIDIA card wins again, though the margin is small: 170 versus 164, a 3.7% lead. The PassMark DirectX 12 test is a perfect tie at 72 points for both GPUs, which the database credits to NVIDIA based on the tiebreaker convention. The Arc B570's wins come in the 2D and compute categories. In PassMark G2D, the Intel card scores 661 against 637, a 3.6% advantage. In PassMark GPU Compute, the Arc B570 wins by a negligible 0.1%, scoring 7281 versus 7276.

When looking at overall averages, the RTX 3080 Mobile holds a clear lead. Its average benchmark score is 23628, while the Arc B570 averages 20556, a difference of roughly 15%. The RTX 3080 Mobile also sits in the 69th percentile of all GPUs in the database, compared to the 65th percentile for the Arc B570. The NVIDIA part's nearest rivals include the GeForce GTX TITAN Z at an average score of 23736 (-0.5%), the RTX 3070 Ti Mobile at 23518 (+0.5%), and the Radeon RX 9070 at 23877 (-1%). The Arc B570, meanwhile, sits almost exactly level with the RTX 3070 Mobile, which averages 20534 (+0.1%), and the Intel Arc A750 at 20582 (-0.1%).

Where Each One Wins

The NVIDIA GeForce RTX 3080 Mobile is the stronger choice for compute-heavy workloads and older DirectX API performance. Its 25.5% lead in OpenCL and 84.6% lead in DirectX 10 are the two most significant margins in this comparison. For users running OpenCL-accelerated applications, such as certain rendering or analysis tools, the RTX 3080 Mobile provides substantially higher throughput. The Geekbench Vulkan result also favors NVIDIA, with a 7.5% advantage, which suggests the RTX 3080 Mobile handles Vulkan titles with a slight edge. DirectX 11 and DirectX 9 workloads also favor the NVIDIA part, with margins of 23.7% and 3.7% respectively. The DirectX 12 tie at 72 points means neither GPU has a clear claim in that API, though the database assigns the win to NVIDIA.

The Intel Arc B570, by contrast, wins in the 2D rasterization test (PassMark G2D) with a 3.6% margin, and it essentially matches the RTX 3080 Mobile in GPU compute, winning by only 0.1%. The 3DMark Steel Nomad DX12 result is the most notable Intel win, showing the Arc B570 slightly ahead in a modern DirectX 12 workload. This suggests the Xe2-HPG architecture is competitive in current-generation gaming scenarios, even if it lags in older APIs. The Arc B570 also has a higher pixel rate (200.0 GPixel/s versus 148.3 GPixel/s) and a higher texture rate (360.0 GTexel/s versus 296.6 GTexel/s), which aligns with its strong 3DMark showing.

The practical takeaway from the benchmark data is that the RTX 3080 Mobile is a more well-rounded performer, particularly for compute and legacy API compatibility. The Arc B570 is a capable contender in modern DirectX 12 and 2D workloads, but its overall average score trails by roughly 15%. The Arc B570's percentile ranking of 65 versus the RTX 3080 Mobile's 69 confirms that NVIDIA holds the higher position in the database's global GPU ranking.

Architecture Differences

The two GPUs come from different foundries and process nodes. The NVIDIA GeForce RTX 3080 Mobile uses the GA104 chip built on Samsung's 8 nm process, while the Intel Arc B570 uses the BMG-G21 chip fabricated by TSMC on a 5 nm node. The Intel part packs more transistors: 19,600 million versus 17,400 million, but on a smaller die, 272 mm² compared to 392 mm². This gives the Arc B570 a much higher transistor density of 72.1M per mm², versus 44.4M per mm² for the RTX 3080 Mobile.

The NVIDIA architecture is Ampere, while Intel uses Xe2-HPG, also known as Battlemage for the Arc 5 generation. The RTX 3080 Mobile features 6144 shading units, 192 texture mapping units, and 96 render output units. It also includes 48 ray tracing cores and 192 tensor cores, which are absent from the Arc B570's specification sheet. The Intel part has 2304 shading units, 144 TMUs, and 80 ROPs, along with 18 ray tracing cores. Despite having far fewer shading units, the Arc B570 clocks much higher: 2500 MHz base and boost, compared to 1110 MHz base and 1545 MHz boost for the RTX 3080 Mobile.

Memory configurations differ significantly. The RTX 3080 Mobile has 8 GB of GDDR6 on a 256-bit bus, yielding 448.0 GB/s of bandwidth. The Arc B570 offers 10 GB of GDDR6 on a 160-bit bus, resulting in 380.0 GB/s of bandwidth. The NVIDIA part has a higher memory bandwidth, but the Intel card has more capacity. The RTX 3080 Mobile's memory runs at 1750 MHz (14 Gbps effective), while the Arc B570's memory runs at 2375 MHz (19 Gbps effective). The higher clock speed partially compensates for the narrower bus.

In terms of compute throughput, the RTX 3080 Mobile delivers 18.98 TFLOPS of FP32 and the same 18.98 TFLOPS of FP16 (1:1 ratio). The Arc B570 delivers 11.52 TFLOPS of FP32 but 23.04 TFLOPS of FP16 (2:1 ratio). This means the Intel card has a significant advantage in half-precision compute, while NVIDIA leads in single-precision. The power draw also differs: the RTX 3080 Mobile is rated at 115 W TDP, while the Arc B570 is rated at 150 W TDP. The Intel card requires a single 8-pin power connector and a 450 W suggested PSU, while the RTX 3080 Mobile lists no power connectors as it is designed for portable devices.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce RTX 3080 Mobile has an average benchmark score of 23628, compared to 20556 for the Intel Arc B570. This puts the RTX 3080 Mobile in the 69th percentile of all GPUs, versus the 65th percentile for the Arc B570.

Q: How do the two GPUs compare in DirectX 12 performance?

A: In the 3DMark Steel Nomad DX12 test, the Intel Arc B570 scores 2649 versus 2644 for the RTX 3080 Mobile, a margin of 0.2%. However, in the PassMark DirectX 12 test, both GPUs score exactly 72 points, resulting in a tie that the database credits to NVIDIA.

Q: What is the memory bandwidth difference?

A: The RTX 3080 Mobile has 448.0 GB/s of bandwidth from 8 GB of GDDR6 on a 256-bit bus. The Arc B570 has 380.0 GB/s from 10 GB of GDDR6 on a 160-bit bus. NVIDIA leads in bandwidth, while Intel offers 2 GB more capacity.

Q: Which GPU is better for OpenCL compute workloads?

A: The RTX 3080 Mobile is significantly better, scoring 104831 in Geekbench OpenCL versus 83514 for the Arc B570, a 25.5% advantage. The PassMark GPU Compute test, however, shows both GPUs nearly identical at 7276 and 7281 respectively.

Q: What are the process node and transistor differences?

A: The RTX 3080 Mobile uses Samsung's 8 nm process with 17,400 million transistors on a 392 mm² die. The Arc B570 uses TSMC's 5 nm process with 19,600 million transistors on a 272 mm² die, resulting in a higher transistor density of 72.1M per mm² versus 44.4M per mm².

Q: Does the Arc B570 have tensor cores?

A: No, the Intel Arc B570 specification does not list tensor cores. The RTX 3080 Mobile has 192 tensor cores, which support its Ampere architecture's AI-accelerated features.

Specification Differences

| Specification | NVIDIA GeForce RTX 3080 Mobile | Intel Arc B570 |

| --- | --- | --- |

| Architecture | Ampere | Xe2-HPG |

| Generation | GeForce 30 Mobile | Battlemage (Arc 5) |

| Process Node | 8 nm | 5 nm |

| Foundry | Samsung | TSMC |

| Transistors | 17,400 million | 19,600 million |

| Die Size | 392 mm² | 272 mm² |

| Transistor Density | 44.4M / mm² | 72.1M / mm² |

| Base Clock | 1110 MHz | 2500 MHz |

| Boost Clock | 1545 MHz | 2500 MHz |

| Memory Clock | 1750 MHz (14 Gbps effective) | 2375 MHz (19 Gbps effective) |

| Memory Size | 8 GB | 10 GB |

| Memory Bus Width | 256 bit | 160 bit |

| Memory Bandwidth | 448.0 GB/s | 380.0 GB/s |

| Shading Units | 6144 | 2304 |

| TMUs | 192 | 144 |

| ROPs | 96 | 80 |

| Ray Tracing Cores | 48 | 18 |

| Tensor Cores | 192 | None |

| Pixel Rate | 148.3 GPixel/s | 200.0 GPixel/s |

| Texture Rate | 296.6 GTexel/s | 360.0 GTexel/s |

| FP32 Performance | 18.98 TFLOPS | 11.52 TFLOPS |

| FP16 Performance | 18.98 TFLOPS (1:1) | 23.04 TFLOPS (2:1) |

| TDP | 115 W | 150 W |

| Power Connectors | None | 1x 8-pin |

| Suggested PSU | None | 450 W |

| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x8 |

| Slot Width | None | Dual-slot |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.1, 3x DisplayPort 2.1 |

| Dimensions | None | 272 mm (10.7 inches) length, 115 mm (4.5 inches) height |

| Production Status | End-of-life | Active |

| Release Date | 2021-01-11 | 2025-01-15 |

| Predecessor | GeForce 20 Mobile | Alchemist |

| Launch MSRP | None | 219 USD |